Unlock instant, AI-driven research and patent intelligence for your innovation.

A feature extraction method for image scene recognition

A feature extraction and scene recognition technology, applied in the field of image scene recognition, can solve the problems of difficult subject features, combination, high dimensionality, etc., and achieve the effect of improving recognition accuracy

Inactive Publication Date: 2017-06-16
JILIN UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] By disclosing a dimensionality reduction method for Object Bank features, it solves the technical problem that its dimensionality is too high and it is difficult to combine with theme features

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A feature extraction method for image scene recognition
  • A feature extraction method for image scene recognition
  • A feature extraction method for image scene recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0107]The present invention relates to a feature extraction method for image scene recognition. The details involved in the technical solution of the present invention will be further described in detail below in conjunction with the accompanying drawings and two embodiments. This embodiment uses a personal computer (PC) for simulation, and its software is based on a 64-bit Windows 7 operating system and a Matlab 2013a simulation environment. The two embodiments are respectively: outdoor scene recognition and sports scene recognition.

[0108] a. Outdoor scene recognition: Using the publicly available LabelMe eight-category outdoor scene dataset, all images in the dataset have been marked into eight categories, and the eight categories and the number of images contained in them are: beach 360, forest 328, highway Road 260, city 308, mountain 374, field 410, street 292, high-rise 356. The LabelMe eight-type outdoor scene data set can be found in the paper: Oliva A, Torralba A....

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a feature extraction method for image scene recognition, which includes two steps of mining information in a group of known training images and identifying test images to be identified, wherein the first step includes pre-processing the images. Processing; extracting the target feature of the image; reducing the dimension of the target feature; executing the LDA model training algorithm; generating the scene environment feature of the training image; feature combination; executing the SVM training algorithm. The second step includes preprocessing the test image; generating the codeword of the test image; generating the scene environment feature of the test image; extracting the target feature of the test image; reducing the target feature dimension of the test image; SVM classifiers generate image categories. The invention reduces the calculation amount of the existing method, expands the application range and improves the recognition accuracy.

Description

technical field [0001] The invention belongs to image scene recognition technology, in particular to a feature extraction method for image scene recognition. Background technique [0002] The purpose of image scene recognition is to obtain the semantic information of the image and give its category label. It is an important research content in the fields of computer vision, pattern recognition and machine learning, and it is also an indispensable technology in practical fields such as image library management and image retrieval. The method based on bag of features (Bag of Features) and topic model is a research boom in recent years, and many new achievements and progress have been made. This type of method draws on the natural language processing process, treats the image as a collection of local observations and builds a feature bag, uses the feature bag to build a topic model, and generates features or directly generates categories. In addition, the object recognition t...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62
CPCG06N3/02G06F18/21G06F18/23213G06F18/2411
Inventor 臧睦君刘通宋伟伟李阳王珂
Owner JILIN UNIV